Commit Graph

27 Commits

Author SHA1 Message Date
João Salavisa 5143a76e35 fix(agents): emit --dangerously-skip-permissions for Claude CLI passthrough (#1262)
* fix(agents): emit --dangerously-skip-permissions for Claude CLI passthrough (#1261)

Claude ACP declared empty PermSettings in passthrough mode, so the launch path's
PermissionValues map (which carries the profile's DangerouslySkipPermissions
toggle) had no matching CLI-flag mapping to emit. Bypass / auto-approve was
silently ignored. Wire the permission setting to --dangerously-skip-permissions
and skip the key in seedCLIFlags so the toggle does not double-surface in the
curated cli_flags list.

* test(agents): use PermissionKeyDangerouslySkipPermissions constant in claude_acp_test

* test(agents): use constant in claude_acp_test failure message too

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
2026-06-03 10:14:03 +01:00
Carlos Florêncio 7917c95496 feat(backend): inject MCP servers in CLI passthrough mode per agent (#1158) 2026-06-03 00:09:05 +01:00
Carlos Florêncio bf7762d939 fix(agents): split codex acp flags from agentctl auto-approve (#1253) 2026-06-02 23:10:02 +01:00
João Salavisa 6a684211fc fix(agentctl): reap disconnected ACP sessions + MCP child trees (#1249)
* fix(agentctl): reap disconnected ACP sessions + MCP child trees (#1247)

Two independent leaks let opencode acp sessions accumulate indefinitely:

1. instance.Manager never reaped disconnected sessions. StopInstance
   only ran via the kandev DELETE route, so any session whose backend
   went away (UI closed mid-run, WS dropped, opencode failed to emit
   complete) was orphaned forever.
2. Even when DELETE fired, the ACP adapter unconditionally returned
   RequiresProcessKill=false. opencode acp keeps an HTTP server + MCP
   child tree alive after stdin EOF, so closing stdin was a no-op and
   the children re-parented to init.

Fix both:

- Plumb RuntimeConfig.RequiresProcessKill from agents.OpenCodeACP
  through the ExecutorCreateRequest -> CreateInstanceRequest ->
  InstanceConfig -> adapter.Config -> shared.Config chain. acp.Adapter
  now reads cfg.RequiresProcessKill instead of hardcoding false.
- Belt-and-braces: process.Manager.waitForProcessExit timeout fallback
  now killProcessGroup first (only falls back to single-process kill
  if that errors), so any future ACP CLI that ignores stdin EOF still
  gets reaped.
- Add an idle-instance reaper to instance.Manager. Per-instance
  activity middleware tracks inflight HTTP requests + lastActivity;
  a background goroutine sweeps every minute and StopInstance's any
  instance idle past KANDEV_ACP_IDLE_TIMEOUT (default 1h, set to 0
  to disable). Long-lived /agent/stream WS connections keep the
  inflight counter above zero so active sessions are never reaped.
- Validate stdio MCP commands at CreateInstance time via
  exec.LookPath; missing entries are dropped with a warn instead of
  spawning a permanently broken child every session (fixes the
  stale /snap/bin/brave MCP repro in the issue).

Regression tests: process-group kill (parent+child fixture), idle
reaper end-to-end, MCP validation, opencode-acp opt-in vs other
ACP agents' default.

* fix: address PR review feedback on #1247 fix

- idle_reaper: extract reapSingleIdleInstance helper with defer cancel(),
  add reaperStop polling between sweep iterations so Shutdown drains in
  one StopInstance window instead of N * timeout (cubic, claude, greptile).
- instance.Manager: use sync.Once instead of m.mu to gate reaper-stop
  channel close (claude).
- mcpStdioValidationError: tolerate compound Command strings by
  resolving only the first whitespace-delimited token; reject entries
  with neither URL nor Command outright; document agentctl-vs-agent
  PATH skew in Docker/SSH executor modes (claude, greptile, cubic).
- manager_killgroup_test: treat zombie state as dead via /proc/<pid>/stat
  on Linux + bump Eventually window to 15s — CI containers' PID 1 can
  delay harvesting orphans long enough to flake signal(0) probes.
- instance package: add goleak TestMain for the new reaper goroutine
  (coderabbit).
- AGENTS.md: correct SIGKILL vs SIGTERM wording; clarify the timeout
  fallback only fires on ctx.Done (coderabbit, cubic).

---------

Co-authored-by: Kandev Agent <agent@kandev.dev>
2026-06-02 21:46:49 +01:00
Carlos Florêncio 036aee6e19 fix(agents): add Cursor auto-approve and always-allow permission UI (#1198) 2026-05-31 17:13:00 +01:00
José Almeida b109c84e4e fix(backend): pass HTTP MCP servers to ACP agents via AssumeMcpHttp (#1152)
* fix(backend): pass HTTP MCP servers to ACP agents via AssumeMcpHttp

* test(backend): cover AssumeMcpHttp override path with effectiveMcpCapabilities helper
2026-05-29 12:58:51 +01:00
José Almeida 823117ba48 fix: wire MCP config into CLI passthrough (#1078)
* fix: wire MCP config into CLI passthrough

* fix: address passthrough MCP review feedback

* fix: fail fast when passthrough MCP port is missing

* fix: track passthrough MCP config with nil metadata
2026-05-26 11:38:30 +01:00
Carlos Florêncio f1dbad1dbd feat(cli-mode): auto-inject task prompt + dynamic submit sequence + passthrough UX fixes (#923) 2026-05-25 19:14:36 +01:00
Carlos Florêncio 0b2085688b feat(office): autonomous agent management layer (#914) 2026-05-16 20:07:57 +01:00
Carlos Florêncio f97ac8bbc1 feat: streaming agent install, PTY login terminal, docker container UX (#869) 2026-05-11 17:52:05 +01:00
José Almeida 2e2bd441c6 fix(passthrough): apply profile cli_flags to passthrough command (#722)
* fix(passthrough): apply profile cli_flags to passthrough command

PassthroughOptions had no CLIFlagTokens field, so the passthrough
launch path silently dropped profile-configured cli_flags. Mirror the
ACP launch path: resolve via cliflags.Resolve and append the tokens
through StandardPassthrough.BuildPassthroughCommand.

Fixes #718.

* fix(passthrough): skip auto-restart on fast-fail launch errors

A bad CLI flag, missing binary, or auth failure makes the agent
process exit immediately. The auto-restart loop then thrashed
forever, spamming "[Agent exited. Restarting...]" without ever
recovering.

Track the start time of each passthrough process and short-circuit
the restart path when an exit lands within 2s with a non-zero code.
Surface a one-shot terminal banner pointing the user at the likely
fix instead.

* refactor(passthrough): snapshot start time at call site to avoid race

Claude review on PR #722: handlePassthroughExit ran in a goroutine and
read execution.PassthroughStartedAt while the next launch could
concurrently write it. Snapshot the value synchronously in
handlePassthroughStatus and thread it through; isFastFailExit now
takes the start time directly.

Also extracts attemptPassthroughRestart and notifyFastFailExit to
keep handlePassthroughExit under the funlen limit.

* refactor(passthrough): measure fast-fail uptime from status timestamp

Claude review on PR #722: handlePassthroughExit's uptime measurement
folded in the cleanupDelay sleep (~100 ms), so the logged duration was
systematically inflated and a process that died at, say, 1.95 s would
slip past the 2 s cutoff.

Use status.Timestamp (set when the child actually exited) as the exit
time and pass it through to isFastFailExit. notifyFastFailExit now
receives a pre-computed uptime so the log reflects real child runtime.
2026-04-28 00:08:42 +01:00
Carlos Florêncio 2d1a868107 feat: configurable CLI flags per agent profile (#653) 2026-04-20 23:42:14 +01:00
Carlos Florêncio 204fac1cca feat: acp-first profiles, models, and modes (#566) 2026-04-15 13:22:32 +01:00
Carlos Florêncio 663919a52b fix(agents): update gemini ACP flag and claude-agent-acp package org (#482) 2026-03-28 23:11:21 +00:00
João Salavisa af47b778af feat: add ACP-based utility agent inference and generate buttons in changes panel (#420) 2026-03-12 16:19:09 +00:00
Carlos Florêncio 37e6b1bd6d fix: recover from agent MCP timeout during clarification wait (#413) 2026-03-10 22:48:30 +00:00
Carlos Florêncio a2d04a9573 fix: resolve ACP model ID mismatch and promote ACP agents as default (#404) 2026-03-10 18:58:29 +00:00
Carlos Florêncio c73fa7471b fix: resolve clarification MCP timeout with cancel-and-resume flow (#362) 2026-03-05 00:18:57 +00:00
Carlos Florêncio cd96c6f699 feat: install agents on env preparation remote executors (#352) 2026-03-02 22:47:21 +00:00
João Salavisa ae616136bb feat: add utility agents for one-shot AI tasks (#341) 2026-03-02 01:55:39 +00:00
Carlos Florêncio cc9574ffcc feat: claude code auth setup for remote executors (#285)
release / build-web (push) Has been cancelled
release / build-bundles (aarch64-linux-gnu-gcc, arm64, linux, ubuntu-latest, linux-arm64) (push) Has been cancelled
release / build-bundles (amd64, darwin, macos-14, macos-x64) (push) Has been cancelled
release / build-bundles (amd64, linux, ubuntu-latest, linux-x64) (push) Has been cancelled
release / build-bundles (arm64, darwin, macos-14, macos-arm64) (push) Has been cancelled
release / build-bundles (x86_64-w64-mingw32-gcc, amd64, windows, ubuntu-latest, windows-x64) (push) Has been cancelled
release / publish-release (push) Has been cancelled
2026-02-25 21:48:06 +00:00
Carlos Florêncio aea8dc7b67 feat: improve workflows and agent resume (#269) 2026-02-23 23:54:27 +00:00
Carlos Florêncio 40b4de3f1a feat: improve remote executor sprites.dev (#267) 2026-02-23 01:37:02 +00:00
Carlos Florêncio a2e9390e66 feat: improve claude code 2026-02-21 22:05:24 +00:00
Carlos Florêncio 90bec9aaa0 feat: update readme & agent TUI reliability (#239) 2026-02-17 22:59:53 +00:00
Carlos Florêncio 35f8d02a4d feat: improve onboarding dialog (#230) 2026-02-16 16:26:26 +00:00
Carlos Florêncio ee612a42c5 feat: agents.json refactor (#221) 2026-02-14 15:54:11 +00:00